Data-driven distributionally robust optimization using the Wasserstein metric: performance guarantees and tractable reformulations
Publication:1785197
DOI10.1007/S10107-017-1172-1zbMath1433.90095DBLPjournals/mp/EsfahaniK18arXiv1505.05116OpenAlexW2963450292WikidataQ59523500 ScholiaQ59523500MaRDI QIDQ1785197
Daniel Kuhn, Peyman Mohajerin Esfahani
Publication date: 28 September 2018
Published in: Mathematical Programming. Series A. Series B (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/1505.05116
Convex programming (90C25) Minimax problems in mathematical programming (90C47) Stochastic programming (90C15)
Related Items (only showing first 100 items - show all)
Uses Software
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Data-driven chance constrained stochastic program
- A comment on ``Computational complexity of stochastic programming problems
- Models and algorithms for distributionally robust least squares problems
- Simple bounds for the convergence of empirical and occupation measures in 1-Wasserstein distance
- On the rate of convergence in Wasserstein distance of the empirical measure
- Block splitting for distributed optimization
- Quantitative concentration inequalities for empirical measures on non-compact spaces
- Empirical risk minimization for heavy-tailed losses
- Tests of goodness of fit based on the \(L_2\)-Wasserstein distance
- Challenging the empirical mean and empirical variance: a deviation study
- A framework for optimization under ambiguity
- Ambiguous chance constrained problems and robust optimization
- Deriving robust counterparts of nonlinear uncertain inequalities
- Computationally Tractable Counterparts of Distributionally Robust Constraints on Risk Measures
- Multistage Stochastic Optimization
- Robustifying Convex Risk Measures for Linear Portfolios: A Nonparametric Approach
- Distributionally Robust Convex Optimization
- Distributionally Robust Optimization Under Moment Uncertainty with Application to Data-Driven Problems
- Distributionally Robust Optimization and Its Tractable Approximations
- Monotone Approximation of Decision Problems
- TRACTABLE ROBUST EXPECTED UTILITY AND RISK MODELS FOR PORTFOLIO OPTIMIZATION
- Models for Minimax Stochastic Linear Optimization Problems with Risk Aversion
- Ambiguous Risk Measures and Optimal Robust Portfolios
- On the Relation Between Option and Stock Prices: A Convex Optimization Approach
- Worst-Case Value-At-Risk and Robust Portfolio Optimization: A Conic Programming Approach
- The Price of Robustness
- Foundations of Modern Probability
- Integral Probability Metrics and Their Generating Classes of Functions
- Variational Analysis
- Distributionally Robust Stochastic Programming
- Ambiguity in portfolio selection
This page was built for publication: Data-driven distributionally robust optimization using the Wasserstein metric: performance guarantees and tractable reformulations